Repository logo
 

Use of a Deep Recurrent Neural Network to Reduce Wind Noise: Effects on Judged Speech Intelligibility and Sound Quality.

Published version
Peer-reviewed

Change log

Authors

Keshavarzi, Mahmoud 
Zakis, Justin 
Turner, Richard E 
Moore, Brian CJ 

Abstract

Despite great advances in hearing-aid technology, users still experience problems with noise in windy environments. The potential benefits of using a deep recurrent neural network (RNN) for reducing wind noise were assessed. The RNN was trained using recordings of the output of the two microphones of a behind-the-ear hearing aid in response to male and female speech at various azimuths in the presence of noise produced by wind from various azimuths with a velocity of 3 m/s, using the "clean" speech as a reference. A paired-comparison procedure was used to compare all possible combinations of three conditions for subjective intelligibility and for sound quality or comfort. The conditions were unprocessed noisy speech, noisy speech processed using the RNN, and noisy speech that was high-pass filtered (which also reduced wind noise). Eighteen native English-speaking participants were tested, nine with normal hearing and nine with mild-to-moderate hearing impairment. Frequency-dependent linear amplification was provided for the latter. Processing using the RNN was significantly preferred over no processing by both subject groups for both subjective intelligibility and sound quality, although the magnitude of the preferences was small. High-pass filtering (HPF) was not significantly preferred over no processing. Although RNN was significantly preferred over HPF only for sound quality for the hearing-impaired participants, for the results as a whole, there was a preference for RNN over HPF. Overall, the results suggest that reduction of wind noise using an RNN is possible and might have beneficial effects when used in hearing aids.

Description

Keywords

hearing aids, machine learning, neural networks, speech intelligibility and sound quality, wind noise, Acoustics, Auditory Threshold, Female, Hearing Aids, Hearing Loss, Humans, Male, Neural Networks, Computer, Noise, Random Allocation, Speech Acoustics, Speech Intelligibility, Speech Perception, Wind, Young Adult

Journal Title

Trends Hear

Conference Name

Journal ISSN

2331-2165
2331-2165

Volume Title

22

Publisher

SAGE Publications
Sponsorship
Engineering and Physical Sciences Research Council (EP/M026957/1)
HB Allen Charitable Trust (unknown)